The present disclosure relates to systems, non-transitory computer-readable media, and methods for intelligently identifying upload trigger events and/or storage trigger events to selectively store a media recording portion at an in-cabin media capture device and/or transmit the media recording portion to a remote server. For example, utilizing a trigger analysis model, the disclosed systems can analyze transportation service data such as motion data, global position system (GPS) data, audio data, digital incident reports from provider/requestor devices, etc. to identify certain trigger events. These trigger events may include, for instance, a collision event, a transportation irregularity, a confrontation event, provider/requestor media recording requests, among others. In response to identifying a trigger event, the disclosed systems can cause a specific portion of a media recording to be stored in a reserved storage partition of the in-cabin media capture device and can selectively upload the media recording portion to a remote server.
Legal claims defining the scope of protection, as filed with the USPTO.
7. The computer-implemented method of claim 6, wherein initiating the upload of the portion of the first digital video and the second digital video to the remote server comprises initiating the upload of the subset of the first digital video and the second digital video stored in the second memory partition of the in-cabin media capture device.
11. The non-transitory computer-readable medium of claim 8, further comprising instructions that, when executed by the at least one processor, cause the computer system to analyze both the first digital video and the second digital video to detect the trigger event by applying a machine-learning model to the first digital video and the second digital video to identify the trigger event.
12. The non-transitory computer-readable medium of claim 8, wherein generating the media classification for the first digital video and the second digital video comprises determining a type of trigger event from a plurality of trigger event types, a severity class for the trigger event, or a notification class for the trigger event.
14. The non-transitory computer-readable medium of claim 13, further comprising instructions that, when executed by the at least one processor, cause the computer system to initiate the upload of the portion of the first digital video and the second digital video to the remote server by initiating the upload of the subset of the first digital video and the second digital video stored in the second memory partition of the in-cabin media capture device.
18. The system of claim 15, wherein the one or more computing devices are further configured to cause the system to analyze the first digital video and the second digital video to detect the trigger event by applying a machine-learning model to the first digital video and the second digital video to identify the trigger event.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 30, 2020
January 30, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.